© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Qwen2.5-7B-IT
    7. Resid Post - 131k
    9. 19-RESID-POST-AA
    11. 75218
    Prev
    Next
    INDEX
    Explanations

    important

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_19/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     `[
    -0.07
    鹙
    -0.07
    גוד
    -0.07
    `(
    -0.06
    .fullName
    -0.06
    igung
    -0.06
     vowel
    -0.06
    蟫
    -0.06
    ülü
    -0.06
    '].
    -0.06
    POSITIVE LOGITS
     captured
    0.08
    Defined
    0.07
     Passing
    0.07
     seat
    0.07
    ffset
    0.07
     demonstrations
    0.07
    เถ
    0.06
    .DialogInterface
    0.06
     executed
    0.06
     Popular
    0.06
    Activations Density 0.028%

    No Known Activations